def max_batch_delay()

in src/sagemaker_pytorch_serving_container/ts_environment.py [0:0]

• 2 lines of code
• 1 McCabe index (conditional complexity)

    def max_batch_delay(self):  # type: () -> int
        """int: time delay in milliseconds, to wait for incoming requests to be batched,
        before running inference on the server
        """
        return self._max_batch_delay